Skip to main content
Back

Multiple Comparisons: Bonferoni Test definitions

Control buttons has been changed to "navigation" mode.
1/15
  • ANOVA
    A statistical method for comparing means across three or more groups to detect any significant differences among them.
  • Null Hypothesis
    An initial claim stating all group means are equal, serving as the baseline for statistical testing.
  • Post Hoc Test
    A follow-up analysis performed after rejecting the main hypothesis to identify which specific group means differ.
  • Bonferroni Test
    A correction method for multiple comparisons that adjusts significance levels to control the chance of false positives.
  • Pairwise Comparison
    An analysis involving the evaluation of all possible pairs of group means to determine where differences exist.
  • Mean Square Error
    A value from ANOVA representing the average of squared differences within groups, used as a variance estimate.
  • Degrees of Freedom
    A parameter based on sample size and number of groups, crucial for determining critical values in statistical tests.
  • Test Statistic
    A calculated value, such as a t-score, used to assess the evidence against the null hypothesis in each comparison.
  • P Value
    A probability measure indicating the likelihood of observing the data if the null hypothesis is true.
  • Adjusted P Value
    A modified probability accounting for multiple tests, typically found by multiplying the original value by the number of comparisons.
  • Alpha Level
    A threshold probability, often set at 0.05, used to decide whether to reject the null hypothesis.
  • Sample Size
    The number of observations in each group, impacting the calculation of test statistics and error estimates.
  • Combinations
    A mathematical concept used to count the number of unique pairs formed from several groups for comparison.
  • Two-Tailed Test
    A statistical test that considers differences in both directions, checking for any inequality between group means.
  • Variance Within
    The measure of variability among data points inside each group, reflected by the mean square error in ANOVA.